{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JDV6GKG4PHI2CQ5EZ42XVXL7XC","short_pith_number":"pith:JDV6GKG4","canonical_record":{"source":{"id":"2006.15874","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T08:55:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"45a83dd9ea55bca9f0ba4ebf495d12ca00b79b20841fdc58dda28263278a8a31","abstract_canon_sha256":"a0897f0a4d921a8e5a0e428a5be298b52c3f0afa4577369047ae7f3194f2d98e"},"schema_version":"1.0"},"canonical_sha256":"48ebe328dc79d1a143a4cf357add7fb88cd054b8bce109fc6f390ab4d0243a64","source":{"kind":"arxiv","id":"2006.15874","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15874","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15874v2","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15874","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_12","alias_value":"JDV6GKG4PHI2","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_16","alias_value":"JDV6GKG4PHI2CQ5E","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_8","alias_value":"JDV6GKG4","created_at":"2026-07-05T01:15:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JDV6GKG4PHI2CQ5EZ42XVXL7XC","target":"record","payload":{"canonical_record":{"source":{"id":"2006.15874","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T08:55:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"45a83dd9ea55bca9f0ba4ebf495d12ca00b79b20841fdc58dda28263278a8a31","abstract_canon_sha256":"a0897f0a4d921a8e5a0e428a5be298b52c3f0afa4577369047ae7f3194f2d98e"},"schema_version":"1.0"},"canonical_sha256":"48ebe328dc79d1a143a4cf357add7fb88cd054b8bce109fc6f390ab4d0243a64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:51.385371Z","signature_b64":"i6U/mmKb7GhlieTBy7TZpHIlmq/nXbfKdsjkvNoY75JttP/xllTx8VN3AApviDSJSyqZXMTz1v8wt+U/5n1vAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48ebe328dc79d1a143a4cf357add7fb88cd054b8bce109fc6f390ab4d0243a64","last_reissued_at":"2026-07-05T01:15:51.384857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:51.384857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.15874","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:15:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uD9dtaj6iNkRLcOC1CJaDSTpnGdJ3cbhpiCea2uVwWAzzrk9NriS9ZToyq/zi1hZvyGpBNse7+HSgCI4g77IDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:47:38.058830Z"},"content_sha256":"23f47107c68d8cf2ea48b0a0055e9624d64bac15d40585866a184b14f095b624","schema_version":"1.0","event_id":"sha256:23f47107c68d8cf2ea48b0a0055e9624d64bac15d40585866a184b14f095b624"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JDV6GKG4PHI2CQ5EZ42XVXL7XC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decorrelated Clustering with Data Selection Bias","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bai Wang, Chuan Shi, Jiawei Liu, Kun Kuang, Shaohua Fan, Xiao Wang","submitted_at":"2020-06-29T08:55:50Z","abstract_excerpt":"Most of existing clustering algorithms are proposed without considering the selection bias in data. In many real applications, however, one cannot guarantee the data is unbiased. Selection bias might bring the unexpected correlation between features and ignoring those unexpected correlations will hurt the performance of clustering algorithms. Therefore, how to remove those unexpected correlations induced by selection bias is extremely important yet largely unexplored for clustering. In this paper, we propose a novel Decorrelation regularized K-Means algorithm (DCKM) for clustering with data se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15874","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.15874/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:15:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dVNBtF7WuhzZVUbxtBxTh/JiKUDRqYJwWZwU3Sf/PUSt838eIZEFeDLpqNayFHN1puyjIqEOUcQiSVN7lfhADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:47:38.059380Z"},"content_sha256":"a3deaeac563e12ecb71f4f948956629364c77ad1ec1f4af901cad349ffbf01f2","schema_version":"1.0","event_id":"sha256:a3deaeac563e12ecb71f4f948956629364c77ad1ec1f4af901cad349ffbf01f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JDV6GKG4PHI2CQ5EZ42XVXL7XC/bundle.json","state_url":"https://pith.science/pith/JDV6GKG4PHI2CQ5EZ42XVXL7XC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JDV6GKG4PHI2CQ5EZ42XVXL7XC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T12:47:38Z","links":{"resolver":"https://pith.science/pith/JDV6GKG4PHI2CQ5EZ42XVXL7XC","bundle":"https://pith.science/pith/JDV6GKG4PHI2CQ5EZ42XVXL7XC/bundle.json","state":"https://pith.science/pith/JDV6GKG4PHI2CQ5EZ42XVXL7XC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JDV6GKG4PHI2CQ5EZ42XVXL7XC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JDV6GKG4PHI2CQ5EZ42XVXL7XC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a0897f0a4d921a8e5a0e428a5be298b52c3f0afa4577369047ae7f3194f2d98e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T08:55:50Z","title_canon_sha256":"45a83dd9ea55bca9f0ba4ebf495d12ca00b79b20841fdc58dda28263278a8a31"},"schema_version":"1.0","source":{"id":"2006.15874","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15874","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15874v2","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15874","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_12","alias_value":"JDV6GKG4PHI2","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_16","alias_value":"JDV6GKG4PHI2CQ5E","created_at":"2026-07-05T01:15:51Z"},{"alias_kind":"pith_short_8","alias_value":"JDV6GKG4","created_at":"2026-07-05T01:15:51Z"}],"graph_snapshots":[{"event_id":"sha256:a3deaeac563e12ecb71f4f948956629364c77ad1ec1f4af901cad349ffbf01f2","target":"graph","created_at":"2026-07-05T01:15:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.15874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most of existing clustering algorithms are proposed without considering the selection bias in data. In many real applications, however, one cannot guarantee the data is unbiased. Selection bias might bring the unexpected correlation between features and ignoring those unexpected correlations will hurt the performance of clustering algorithms. Therefore, how to remove those unexpected correlations induced by selection bias is extremely important yet largely unexplored for clustering. In this paper, we propose a novel Decorrelation regularized K-Means algorithm (DCKM) for clustering with data se","authors_text":"Bai Wang, Chuan Shi, Jiawei Liu, Kun Kuang, Shaohua Fan, Xiao Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T08:55:50Z","title":"Decorrelated Clustering with Data Selection Bias"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15874","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:23f47107c68d8cf2ea48b0a0055e9624d64bac15d40585866a184b14f095b624","target":"record","created_at":"2026-07-05T01:15:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a0897f0a4d921a8e5a0e428a5be298b52c3f0afa4577369047ae7f3194f2d98e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T08:55:50Z","title_canon_sha256":"45a83dd9ea55bca9f0ba4ebf495d12ca00b79b20841fdc58dda28263278a8a31"},"schema_version":"1.0","source":{"id":"2006.15874","kind":"arxiv","version":2}},"canonical_sha256":"48ebe328dc79d1a143a4cf357add7fb88cd054b8bce109fc6f390ab4d0243a64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48ebe328dc79d1a143a4cf357add7fb88cd054b8bce109fc6f390ab4d0243a64","first_computed_at":"2026-07-05T01:15:51.384857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:15:51.384857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i6U/mmKb7GhlieTBy7TZpHIlmq/nXbfKdsjkvNoY75JttP/xllTx8VN3AApviDSJSyqZXMTz1v8wt+U/5n1vAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:15:51.385371Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.15874","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23f47107c68d8cf2ea48b0a0055e9624d64bac15d40585866a184b14f095b624","sha256:a3deaeac563e12ecb71f4f948956629364c77ad1ec1f4af901cad349ffbf01f2"],"state_sha256":"f0e6c1b29aee9446ff50451385f78680ac7898c5a9d4c120252d9f2da5de07f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hFSPWULjVP1t7gNALn1G7YIqJBQW0Rl4w7cKfEmXbzELJztLnjBcULH5gN/a4Y1cUzvuBxrgFis2ABDEK9ygAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:47:38.064953Z","bundle_sha256":"590bea8962c4af01af7fb82a4426295a9313bb234933f1906cafb73e2e92d804"}}